<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuned-DatasetQAS-Squad-ID-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6868
- Exact Match: 45.1218
- F1: 61.3575
- Precision: 62.6921
- Recall: 67.7425
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 2.4472 | 0.5 | 1023 | 2.2865 | 29.5933 | 42.4059 | 43.5205 | 52.5488 |
| 1.8722 | 1.0 | 2046 | 1.8562 | 39.5825 | 55.5286 | 56.6097 | 63.1751 |
| 1.6329 | 1.5 | 3069 | 1.7271 | 42.6516 | 59.0745 | 60.4591 | 65.8650 |
| 1.5391 | 2.0 | 4092 | 1.6703 | 43.7412 | 60.5632 | 62.1124 | 67.0088 |
| 1.4011 | 2.5 | 5115 | 1.6518 | 44.4565 | 61.1817 | 62.7045 | 66.6741 |
| 1.3955 | 3.0 | 6138 | 1.6557 | 45.0803 | 62.3404 | 63.2191 | 68.5525 |
| 1.2678 | 3.5 | 7161 | 1.6473 | 45.3131 | 61.8217 | 63.1073 | 67.9864 |
| 1.2641 | 4.0 | 8184 | 1.6277 | 45.5627 | 61.9713 | 63.2872 | 68.0141 |
| 1.1456 | 4.5 | 9207 | 1.6868 | 45.1218 | 61.3575 | 62.6921 | 67.7425 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2
